🔥Telegram İfşa

🚀 Introducing 𝗦𝗲𝗮𝗿𝗰𝗵-𝗥𝟭 – the first 𝗿𝗲𝗽𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻 𝗼𝗳 𝗗𝗲𝗲𝗽𝘀𝗲𝗲𝗸-𝗥𝟭 (𝘇𝗲𝗿𝗼) for training reasoning and search-augmented LLM agents with reinforcement learning! This is a step towards training an 𝗼𝗽𝗲𝗻-𝘀𝗼𝘂𝗿𝗰𝗲 𝗢𝗽𝗲𝗻𝗔𝗜 “𝗗𝗲𝗲𝗽

Our NAACL 2025 findings paper demonstrates that securing AI agents requires more than off-the-shelf defenses—adaptive attacks continuously evolve to bypass them. If you have any questions or want to discuss more, feel free to reach out!

🤖What makes GRPO work? Rejection Sampling→Reinforce→GRPO - RS is underrated - Key of GRPO: implicitly remove prompts without correct answer - Reinforce+Filtering > GRPO (better KL) 💻github.com/RLHFlow/Minima… 📄arxiv.org/abs/2504.11343 👀RAFT was invited to ICLR25! Come & Chat☕️

Surprised by the small performance gap between RAFT and Reinforce/GRPO. We may need more fine-grained negative signals to better guide learning.🧐

We introduce Gradient Variance Minimization (GVM)-RAFT, a principled dynamic sampling strategy that minimizes gradient variance to improve the efficiency of chain-of-thought (CoT) training in LLMs. – Achieves 2–4× faster convergence than RAFT – Improves accuracy on math

Reinforcement learning enables LLMs to beat humans on programming/math competitions and has driven recent advances (OpenAI's o-series, Anthropic's Claude 4) Will RL enable broad generalization in the same way that pretraining does? Not with current techniques 🧵 1/7

🚀 Excited to share that the Workshop on Mathematical Reasoning and AI (MATH‑AI) will be at NeurIPS 2025! 📅 Dec 6 or 7 (TBD), 2025 🌴 San Diego, California

🪜Introducing: StepWiser🦉 📝: arxiv.org/abs/2508.19229 - Reframes stepwise reward modeling as a reasoning task: outputs CoT + judgment. - Trained by RL using relative outcomes of rollouts. Results: (1) SOTA performance on ProcessBench! (2) Improves policy at train time. (3)

PROF🌀Right answer, flawed reason?🤔🌀 📄arxiv.org/pdf/2509.03403 Excited to share our work: PROF-PRocess cOnsistency Filter! 🚀 Challenge: ORM is blind to flawed logic, and PRM suffers from reward hacking. Our method harmonizes strengths of PRM & ORM. #LLM #ReinforcementLearning

💥Thrilled to share our new work Reinforce-Ada, which fixes signal collapse in GRPO 🥳No more blind oversampling or dead updates. Just sharper gradients, faster convergence, and stronger models. ⚙️ One-line drop-in. Real gains. arxiv.org/html/2510.0499… github.com/RLHFlow/Reinfo…

Why does Muon outperform Adam—and how? 🚀Answer: Muon Outperforms Adam in Tail-End Associative Memory Learning Three Key Findings: > Associative memory parameters are the main beneficiaries of Muon, compared to Adam. > Muon yields more isotropic weights than Adam. > In

Where is exploration most impactful in LLM reasoning? The initial tokens! They shape a sequence's entire semantic direction, making early exploration crucial. Our new work, Exploratory Annealed Decoding (EAD), is built on this insight. By starting with high temperature and

🌀Agent Learning via Early Experience🌀 📝: arxiv.org/abs/2510.08558 - SFT for agents is sparse; RL on long-horizons is hard We provide new mid-training signals that work: 1) Implicit next state world modeling task 2) Self-reflection on alternate states - Strong improvements over

😃 thanks, google!